Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Enriching LIME with Inductive Logic Programming: Explaining Deep Learning Classifiers with Logic Rules in a Companion System Framework

Publication

Enriching LIME with Inductive Logic Programming: Explaining Deep Learning Classifiers with Logic Rules in a Companion System Framework

Rabold, Johannes (2022): Enriching LIME with Inductive Logic Programming: Explaining Deep Learning Classifiers with Logic Rules in a Companion System Framework, Bamberg: Otto-Friedrich-Universität, doi: 10.20378/irb-46527.

Details

Faculty/Chair
Author
Rabold, Johannes
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2022
Pages
v, 52, Illustrationen
Supervisor
Language
English
Remark

Masterarbeit, Otto-Friedrich-Universität Bamberg, 2018

DOI
Licence
URN
Abstract

With the rise of black-box classifiers like Deep Learning networks, the need for interpretable and complete explanations for them becomes apparent. Users need to have the possibility to ask why a classifier inferred a particular result. Logic clauses induced by Inductive Logic Programming systems are superior in expressibility over visual explanations alone.

This thesis uses the ideas of LIME, a visual explanation framework, and enriches it with an ILP component to get comprehensible and powerful explanations for the inference results of Deep Learning Networks for images. The background knowledge for the predicates is obtained both automatically and by an annotation system that lets humans annotate labels and relations. The human labeling system and the explanation component form a Companion System where not only AI helps the user but also the other way round.

GND Keywords
Künstliche Intelligenz
Deep learning
Induktive Logik
System
Framework <Informatik>
Keywords
Explainable AI, Deep Learning, Inductive Logic Programming, LIME, Companion System
Local Interpretable Model-Agnostic Explanations
DDC Classification
004 Computer science
RVK Classification
ST 301
Type
Masterthesis
URI
Activation date
2023-02-01

Permalink: https://fis.uni-bamberg.de/handle/uniba/46527 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.